检索结果-内蒙古大学图书馆

Joint Beam Management and SLAM for mmWave communication Systems

IEEE Transactions on communications 2023年第10期71卷 6162-6179页

作者： Que, Hang Yang, Jie Wen, Chao-Kai Xia, Shuqiang Li, Xiao Jin, Shi Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Frontiers Science Center for Mobile Information Communication and Security Nanjing210096 China Institute of Communications Engineering National Sun Yat-sen University Kaohsiung80424 Taiwan Zte Corporation Shenzhen518055 China State Key Laboratory of Mobile Network and Mobile Multimedia Shenzhen518055 China Southeast University National Mobile Communications Research Laboratory Frontiers Science Center for Mobile Information Communication and Security Nanjing210096 China

The millimeter-wave (mmWave) communication technology, which employs large-scale antenna arrays, enables inherent sensing capabilities. Simultaneous localization and mapping (SLAM) can utilize channel multipath angle estimates to realize integrated sensing and communication design in 6G communication systems. However, existing works have ignored the significant overhead required by the mmWave beam management when implementing SLAM with angle estimates. This study proposes a joint beam management and SLAM design that utilizes the strong coupling between the radio map and channel multipath for simultaneous beam management, localization, and mapping. In this approach, we first propose a hierarchical sweeping and sensing service design. The path angles are estimated in the hierarchical sweeping, enabling angle-based SLAM with the aid of an inertial measurement unit (IMU) to realize sensing service. Then, feature-aided tracking is proposed that utilizes prior angle information generated from the radio map and IMU. Finally, a switching module is introduced to enable flexible switching between hierarchical sweeping and feature-aided tracking. Simulations show that the proposed joint design can achieve sub-meter level localization and mapping accuracy (with an error © 1972-2012 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Fabrication and characterisation of La0.8Sr0.2CrO3-ITO thermocouples for high-temperature sensing

引用

International Journal of Nanomanufacturing 2022年第1期18卷 1-8页

作者： Chen, Bohan Huang, Manguo Zhang, Meiju Liang, Xiaobo Liu, Dan Wang, Lingyan Niu, Gang Zhang, Zhongkai Tian, Bian Shi, Peng Ren, Wei Electronic Materials Research Laboratory Key Laboratory of the Ministry of Education and International Center for Dielectric Research School of Electronic and Information Engineering Xi’an Jiaotong University Xi’an710049 China Beijing Changcheng Aeronautic Measurement and Control Technology Research Institute Beijing101111 China Aviation Key Laboratory of Science and Technology on Special Condition Monitoring Sensor Technology Beijing101111 China State Key Laboratory for Mechanical Manufacturing Systems Engineering School of Mechanical Engineering Xi’an Jiaotong University Xi’an710049 China

La0.8Sr0.2CrO3-ITO thermocouples were successfully fabricated by screen printing. The La0.8Sr0.2CrO3 powder used for screen printing was obtained by the sol-gel method. The highest thermal voltage output was maintained at 270 mV at 1270°C. The microstructure of La0.8Sr0.2CrO3 and ITO electrode films were analysed by SEM. Thermoelectric response test was implemented to measure the performance of La0.8Sr0.2CrO3-ITO thermocouple by three times of thermal cycles. The results indicated that La0.8Sr0.2CrO3-ITO thermocouple showed good stability at high temperature. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Screen printing

来源：评论

学校读者我要写书评

暂无评论

Strip Weld Inspection Based on Improved VGG16

Strip Weld Inspection Based on Improved VGG16

引用

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Sisi Fu Yuan Chen Dexin Xian Shiyuan Kong Hao Wang Jinsong Wang School of Optoelectronic Engineering Changchun University of Science and Technology Zhongshan Guangdong China School of Measurement and Control Technology and Communication Engineering Harbin University of Science and Technology Harbin Heilongjiang China School of Optoelectronic Engineering Zhongshan Institute of Changchun University of Science and Technology Zhongshan Guangdong China School of Optoelectronic Engineering Changchun University of Science and Technology Zhongshan Institute of Changchun University of Science and Technology Zhongshan Guangdong China

As one of the indispensable materials in modern industry, high precision and high efficiency defect detection of strip weld has become an important part of production and quality control. In response to the shortcomings of the existing strip weld detection technology with low detection accuracy, this paper proposes a deep learning based strip weld defect detection and classification technique. First, the CBAM attention mechanism is introduced into the network structure to improve the attention to important features; second, the traditional convolution layer is replaced by using the dilated convolution to reduce the computation while increasing the perceptual field; finally, the original ReLU activation function is replaced by the PReLU activation function to effectively overcome the problem of neuron death in the Relu activation function. The improved model finally achieves a recognition rate of 98.1% in the test set, which is 22.1% higher than that of the unimproved model, greatly improving the accuracy and robustness of the algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deployment & Evaluation of Modern Ros2 Navigation Algorithms for High Autonomy in Complex Environments

SSRN

引用

SSRN 2024年

作者： Horelican, Tomas Zalud, Ludek Central European Institute of Technology Brno University of Technology Brno 61200 Czech Republic Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Brno 61600 Czech Republic

The next-generation Robot Operating System (ROS2) framework has been gaining wider adoption among research as well as commercial applications thanks to its high modularity and attention to performance, safety, and deterministic behavior. The open-source community-driven Navigation2 project provides various latest higher-level algorithm implementations realized on top of the ROS2 foundation, relating to localization, mapping, and navigation. Although these algorithms have been thoroughly evaluated individually, a full solution integration still warrants more testing. This paper will assess the effectiveness and reliability of several of the available algorithms in complete navigation task scenarios in terms of times to reach the desired goal, planning and navigation failures, dynamic obstacle avoidance handling, and goal reaching precision. Configuration and deployment steps will be outlined for reproducibility. Directions for future extension options will also be mentioned based on the wider state-of-the-art situation in the field. All tests were performed using a custom-developed differential-drive robotic platform, where the Navigation2 features have been seamlessly integrated into our system. © 2024, The Authors. All rights reserved.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Ensemble Based Deep Learning Approach for Attack Detection in IoT Network

arXiv

引用

arXiv 2022年

作者： Ahmed, Mir Shahnawaz Shah, Shahid Mehraj Communication Control Learning Lab Department of Electronics & Communication Engineering National Institute of Technology Srinagar India

The Internet of Things (IoT) has altered living by controlling devices/things over the Internet. IoT has specified many smart solutions for daily problems, transforming cyber-physical systems (CPS) and other classical fields into smart regions. Most of the edge devices that make up the Internet of Things have very minimal processing power. To bring down the IoT network, attackers can utilise these devices to conduct a variety of network attacks. In addition, as more and more IoT devices are added, the potential for new and unknown threats grows exponentially. For this reason, an intelligent security framework for IoT networks must be developed that can identify such threats. In this paper, we have developed an unsupervised ensemble learning model that is able to detect new or unknown attacks in an IoT network from an unlabelled dataset. The system-generated labelled dataset is used to train a deep learning model to detect IoT network attacks. Additionally, the research presents a feature selection mechanism for identifying the most relevant aspects in the dataset for detecting attacks. The study shows that the suggested model is able to identify the unlabelled IoT network datasets and DBN (Deep Belief Network) outperform the other models with a detection accuracy of 97.5% and a false alarm rate of 2.3% when trained using labelled dataset supplied by the proposed approach. © 2022, CC BY.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An Eco-Driving Technique for Energy Aware Driving with an Electric Vehicle 4

An Eco-Driving Technique for Energy Aware Driving with an El...

引用

4th IEEE International Conference on Computing, communication, and Intelligent Systems, ICCCIS 2023

作者： Katepalli, Bapaiah Moulik, Bedatri Ali, Ahmed M. Soffker, Dirk Amity University Uttar Pradesh Department of Electronics and Communication Engineering ASET Noida201303 India Amity Institute of Technology AIT Amity University Uttar Pradesh Amity Noida201303 India Military Technical College Automotive Engineering Department Cairo11511 Egypt University of Duisburg-Essen Faculty of Engineering Dynamics and Control Duisburg47057 Germany

ISBN: (纸本)9798350306118

Driving habits of individual drivers have shown to have a strong impact on energy consumption and range of electric vehicles. Eco-driving is a popular procedure for improving the range by manipulating multiple factors such as the car speed or providing corrective suggestions related to the route. An optimized eco-driving can be considered for minimizing the energy consumption, taking into account the driving conditions and situations. In this contribution, a driving pattern recognition is considered wherein two indices namely, driving condition index (DCI) and driving situation index (DSI) are used to characterize a certain pattern. Combinations of DCI and DSI are mapped into a representative driving pattern (RDP) matrix. Based on the chosen RDP values, a reference speed for the vehicle is generated and corresponding PI controller parameters tuned within a driver model to realize eco-driving. The eco-driving strategy is optimized for minimization of energy consumption with the help of Pontryagin's minimum principle (PMP) within a constrained action space defined by the DCI and DSI indices. This novel feature allows an event specific optimal solution to be generated rather than a time specific solution. The simulation results prove the efficiency of the optimized eco-driving in preserving the battery energy and charge. It also shows the selection of representative patterns corresponding to actual driving based on DCI and DSI indices. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Cross-border Data Security Risk Analysis and Development Suggestions of the Protection Technologies for Intelligent Connected Vehicles

Cross-border Data Security Risk Analysis and Development Sug...

引用

Information Science, Parallel and Distributed Systems (ISPDS), International Conference on

作者： Xiaolong Huang Chongshi Xin Haojie Ji Wangdong Lu Peng He Yupeng Chen State Key Laboratory of Intelligent Vehicle Safety Technology Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science& Technology University Beijing China Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science& Technology University Beijing China China Automotive Engineering Research Institute Co. Ltd Chongqing China

ISBN: (数字)9798350352719

ISBN: (纸本)9798350352726

In recent years, intelligent connected vehicles (ICVs) have developed quickly and have been progressively introduced into the international market. Nevertheless, the operation of ICVs produces a large amount of important data coming from driving vehicle and necessitating cross-border transit. As the imperfections of the regulatory framework and the infancy of protective solutions for the ICV data, these data are vulnerable to the threats like eavesdropping and tampering during cross-border transmission. The private information, especially the data barred from leaving the country, will be probably leaked to other nations, endangering individual privacy and national security. Thus, the purpose of this manuscript is to analyze the security risks of cross-border data in ICVs and provide risk mitigation strategies. The legal requirements and pertinent cross-border materials need to be sorted out firstly to establish a thorough technical process for cross-border compliance of ICV data. Additionally, the ICV data risk analyses will be performed at every stage of the cross-border process. Furthermore, some efficient risk mitigation methods need to be offered to improve the security and dependability of the across-border data of ICVs. To address the problems associated with cross-border data pertaining to ICVs, a classification method for the cross-border data of ICVs will be presented according to current rules and data categorization schemes. Finally, this manuscript provides theoretical underpinnings and useful references for building a cross-border data security protection system, as well as a thorough analysis of the development patterns of cutting-edge technologies for cross-border data.

关键词： Technological innovation Connected vehicles Law Data security Solids Risk analysis Protection

来源：评论

学校读者我要写书评

暂无评论

A Spectrum Sensing Method Based on CNN-LSTM Deep Neural Network 7

A Spectrum Sensing Method Based on CNN-LSTM Deep Neural Netw...

引用

7th IEEE International Conference on Network Intelligence and Digital Content, IC-NIDC 2021

作者： Zhang, Shujian Xu, Zhan Tian, Lu Yang, Xiaolong Beijing Information Science and Technology University Key Laboratory of Modern Measurement and Control Technology Beijing100101 China School of Information and Communication Engineering Beijing Information Science and Technology University Beijing100101 China

ISBN: (纸本)9781665405829

Spectrum sensing can effectively improve the low utilization of spectrum resources and is one of the crucial components of cognitive radio networks. This paper proposes a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network cascaded spectrum sensing model. The model uses CNN to analyze the Short-Time Fourier transform spectrogram of the blind signal. Then the generated feature vector or feature map is passed to the LSTM according to the timestamp. Finally, it detects a signal in a specific spectrum and classifies the signal type to identify multiple signals accurately. The neural network model improves the detection probability by simultaneously acquiring the spatial and temporal characteristics of the blind signal. The experimental results show that the method in this paper can detect a variety of signals with higher detection probability within a wide range of SNR, especially under the condition of low SNR. © 2021 IEEE.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Cognitive Jammer Time Resource Scheduling With Imperfect Information Via Fuzzy Q-Learning

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年第3期61卷 7422-7434页

作者： Gan, Linchuan Xiong, Kui Liao, Maosen Yu, Xianxiang Cui, Guolong University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Laboratory of Electromagnetic Space Cognition and Intelligent Control Technology Beijing100089 China UESTC Shenzhen Institute for Advanced Study Shenzhen518038 China

Effective strategy generation of the jammer with inaccurate or undetermined information for combating the radar system is a challenging problem and the relevant research is scarce in existing work. This paper aims at exploring this promising topic and proposing a transmitting time slots scheduling strategy generation method for the cognitive jammer with imperfect time-matching information based on fuzzy reinforcement learning. First, the interaction between the jammer and environment is modeled as a Markov decision process (MDP) with uncertain state and continuous action, in which the goal of the jammer in interaction is to maximize accumulated discount pulse transmitting time slot jamming probability. Then, the uncertain pulse repeat intervals (PRIs) of the radar signal is inferred using the fuzzy inference system (FIS), where the inferred reward is evaluated by the correntropy of the inferred radar PRI and the previously measured one, thus presenting the fuzzy Q-learning based time scheduling (TSFQL) algorithm. Finally, numerical simulations in typical scenarios are performed to illustrate the effectiveness and superiority of the TSFQL algorithm over conventional methods. © 1965-2011 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Method of Rolling Bearings Under Different Working Conditions Based on Federated Feature Transfer Learning

Fault Diagnosis Method of Rolling Bearings Under Different W...

引用

Sensing, measurement & Data Analytics in the era of Artificial Intelligence (ICSMD), International Conference on

作者： Shouqiang Kang Jiawei Yang Yulin Sun Yujing Wang Qingyan Wang V.I. Mikulovich School of Measurement-Control and Communication Engineering Harbin University of Science and Technology Harbin China Belarusian State University Minsk Belarus

A rolling bearing fault diagnosis method based on the federated feature transfer learning is proposed for the low accuracy of the diagnosis model in the presence of large differences in data distribution under different working conditions, difficulty in obtaining labeled data and non-sharing of data among different users. This method performs wavelet transformation on the time domain vibration data of rolling bearings to obtain a time-frequency diagram. The priori labeled public data and the multi-user island private data are regarded as the source domain and the target domain. The multi-representation feature extraction structure is introduced to improve the original residual network. Based on an improved residual network and multi-representation features in the source domain and the target domain, every local model and a federated global model are constructed. Through verification of bearing data, the proposed method can establish an effective fault diagnosis model with high fault diagnosis accuracy. It can integrate the knowledge of isolated island data without sharing data among multiple users.

关键词： Fault diagnosis Employee welfare Wavelet transforms Adaptation models Wavelet domain Transfer learning Rolling bearings

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：